Communication and collaboration between deaf people and hearing people is hindered by lack of a common language. Although there has been a lot of research in this domain, there is room for work towards a system that is ubiquitous, non-invasive, works in real-time and can be trained interactively by the user.
The approach utilizes insights from Sign Language Linguistics that American Sign Language morphemes can be differentitated using either of Movement, Location, Orientation, Handshape or Facial Expression of a signer.
Towards this goal we provide two approaches. The datasets utilized for each of these are also released.
- DyFAV: Dynamic Feature Selection and Voting for Real-time Recognition of Fingerspelled Alphabet using Wearables (pdf)
Dr. Sandeep Gupta
Dr. Ayan Banerjee
Dr. Tamako Azuma